Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 3036
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating obligations and interpersonal support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    After negations or expressions of doubt

    np_acts-logits-general · gemini-2.0-flash

    cannot help but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]='\
    -0.72
    OGND
    -0.67
    DoNot
    -0.58
    ggak
    -0.57
    ⓧ
    -0.55
     "{\"
    -0.54
     newData
    -0.53
    thwaite
    -0.53
     Efq
    -0.53
     Brahmin
    -0.52
    POSITIVE LOGITS
     nor
    0.71
     sondern
    0.70
     relever
    0.68
    mbggenerated
    0.66
     للمعارف
    0.65
    nor
    0.60
    而是
    0.59
    又是一
    0.54
     nedenle
    0.52
     estekak
    0.51
    Activations Density 0.220%

    No Known Activations